{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HDWIYL2L46ILWN5K4GU3AXVLA7","short_pith_number":"pith:HDWIYL2L","schema_version":"1.0","canonical_sha256":"38ec8c2f4be790bb37aae1a9b05eab07fe7da6f8b98f93bc46464707d4d614a6","source":{"kind":"arxiv","id":"1708.08552","version":1},"attestation_state":"computed","paper":{"title":"An inexact subsampled proximal Newton-type method for large-scale machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Jason D. Lee, Xuanqing Liu, Yuekai Sun","submitted_at":"2017-08-28T22:47:48Z","abstract_excerpt":"We propose a fast proximal Newton-type algorithm for minimizing regularized finite sums that returns an $\\epsilon$-suboptimal point in $\\tilde{\\mathcal{O}}(d(n + \\sqrt{\\kappa d})\\log(\\frac{1}{\\epsilon}))$ FLOPS, where $n$ is number of samples, $d$ is feature dimension, and $\\kappa$ is the condition number. As long as $n > d$, the proposed method is more efficient than state-of-the-art accelerated stochastic first-order methods for non-smooth regularizers which requires $\\tilde{\\mathcal{O}}(d(n + \\sqrt{\\kappa n})\\log(\\frac{1}{\\epsilon}))$ FLOPS. The key idea is to form the subsampled Newton sub"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1708.08552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-28T22:47:48Z","cross_cats_sorted":["cs.NA","stat.ML"],"title_canon_sha256":"91ab7dbcded274991af7467452ac9ae12e8a0458ddf9eeb10ac928879f73229b","abstract_canon_sha256":"1b5678ee9e42fcc65bfd55b167bb9da15a9f9727794590d5df143f2af0945199"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:27.444328Z","signature_b64":"R4T5tSOFTlg1nJ22UDEaefRjbuqqPNzdPlP5Ld3mCk1ypEn1yvPBt5ohb/bhpLB041Wk7eLPTVRpUUhD1gdBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38ec8c2f4be790bb37aae1a9b05eab07fe7da6f8b98f93bc46464707d4d614a6","last_reissued_at":"2026-05-18T00:36:27.443601Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:27.443601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An inexact subsampled proximal Newton-type method for large-scale machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Jason D. Lee, Xuanqing Liu, Yuekai Sun","submitted_at":"2017-08-28T22:47:48Z","abstract_excerpt":"We propose a fast proximal Newton-type algorithm for minimizing regularized finite sums that returns an $\\epsilon$-suboptimal point in $\\tilde{\\mathcal{O}}(d(n + \\sqrt{\\kappa d})\\log(\\frac{1}{\\epsilon}))$ FLOPS, where $n$ is number of samples, $d$ is feature dimension, and $\\kappa$ is the condition number. As long as $n > d$, the proposed method is more efficient than state-of-the-art accelerated stochastic first-order methods for non-smooth regularizers which requires $\\tilde{\\mathcal{O}}(d(n + \\sqrt{\\kappa n})\\log(\\frac{1}{\\epsilon}))$ FLOPS. The key idea is to form the subsampled Newton sub"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08552","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1708.08552","created_at":"2026-05-18T00:36:27.443702+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.08552v1","created_at":"2026-05-18T00:36:27.443702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08552","created_at":"2026-05-18T00:36:27.443702+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDWIYL2L46IL","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDWIYL2L46ILWN5K","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDWIYL2L","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7","json":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7.json","graph_json":"https://pith.science/api/pith-number/HDWIYL2L46ILWN5K4GU3AXVLA7/graph.json","events_json":"https://pith.science/api/pith-number/HDWIYL2L46ILWN5K4GU3AXVLA7/events.json","paper":"https://pith.science/paper/HDWIYL2L"},"agent_actions":{"view_html":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7","download_json":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7.json","view_paper":"https://pith.science/paper/HDWIYL2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.08552&json=true","fetch_graph":"https://pith.science/api/pith-number/HDWIYL2L46ILWN5K4GU3AXVLA7/graph.json","fetch_events":"https://pith.science/api/pith-number/HDWIYL2L46ILWN5K4GU3AXVLA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7/action/storage_attestation","attest_author":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7/action/author_attestation","sign_citation":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7/action/citation_signature","submit_replication":"https://pith.science/pith/HDWIYL2L46ILWN5K4GU3AXVLA7/action/replication_record"}},"created_at":"2026-05-18T00:36:27.443702+00:00","updated_at":"2026-05-18T00:36:27.443702+00:00"}